submission 25255
AMD FP8 blockwise GEMM · k = 1536 · m = 1024 · n = 3072 · seed = 6251 · fp32/fp8_e4m3fnuz · run 01a006cb-fff2…
●passedReported evidence
Not re-observed recently.
Primary measurement
49.8µsmean of 90
Rank 11 in its comparison group · source-native comparison · observed 2025-05-20
best ns 48766 · mean ns 49802.73333333333 · leaderboard score s 0.00011953008137861258
Identity
implementationsubmission 25255
projectKernelBot user 376
revisionsubmission-25255
workloadk = 1536 · m = 1024 · n = 3072 · seed = 6251 · fp32/fp8_e4m3fnuz
comparison keysha256:49679ed4b957586a…
sourceGPU MODE KernelBot
external idsubmission/25255/benchmark/1
sha256:b55d5f2f056c76e3eb562d9…
Correctness
Marked passed by the source; the correctness policy was not published.
Workload
k1536
m1024
n3072
seed6251
afp8_e4m3fnuz [1024, 1536]
bfp8_e4m3fnuz [3072, 1536]
a_scalefp32 [1024, 12]
b_scalefp32 [24, 12]
definition comparatorkernelbot_eval
Measurements
latency · max51.5 µs · n=90
latency · mean49.8 µs · n=90
latency · min48.8 µs · n=90
latency · std470 ns · n=90
Protocol
harnessreference-kernels eval.py
timerwall_clock
primaryStatisticmean
correctnessReferenceproblem reference implementation
comparabilityFamilygpumode_kernelbot
Environment
gpuAMD Instinct MI300X (gfx942)
Artifacts
No artifacts published with this run.
Replications and notes
No attestations yet.
Community attestations. They never change the evidence level; only a KernelIndex-controlled rerun does.
Add a reproduction or note
Canonical manifest
Show manifestHide manifest
{
"run": {
"kind": "BenchmarkRun",
"spec": {
"status": "passed",
"timing": {
"samples": 90,
"latencyNs": {
"mean": 49803,
"maximum": 51465,
"minimum": 48766
},
"primaryStatistic": "mean"
},
"observedAt": "2025-05-20T07:48:15.770Z",
"measurements": [
{
"unit": "ns",
"value": 470.1225228776578,
"metric": "latency",
"statistic": "std",
"sampleCount": 90
}
],
"sourceNative": {
"source": "gpumode-kernelbot",
"metrics": {
"best_ns": 48766,
"mean_ns": 49802.73333333333,
"leaderboard_score_s": 0.00011953008137861258
},
"benchmark": "amd-fp8-mm/1",
"externalId": "submission/25255"
},
"protocolDigest": "sha256:7c66da4b5866502eb10444a7ba013d0f6bdf1620c55847945008cad2fbf98aec",
"workloadDigest": "sha256:123a5920d4d1c9c68205516418cb0cabff835fa28c7f0d139b48e8dbc1406b14",
"environmentDigest": "sha256:f722892449ed976f3e21b12df8b92b34573fc232883fec6a2f3da399a00abdd5",
"implementationDigest": "sha256:d9d1e5de913c35a0ced9cb92672e13056f48e41376bd7297c1ab7ed5fc8a1ffd"
},
"metadata": {
"name": "kernelbot-25255-k1536-m1024-n3072-seed6251",
"title": "amd-fp8-mm · submission 25255 · case 1",
"labels": {
"torch": "2.8.0.dev20250519+rocm6.3",
"platform": "Linux-5.15.0-136-generic-x86_64-with-glibc2.35"
}
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"protocol": {
"kind": "BenchmarkProtocol",
"spec": {
"harness": {
"name": "reference-kernels eval.py",
"repository": "https://github.com/gpu-mode/reference-kernels"
},
"correctness": {
"reference": "problem reference implementation",
"comparator": "kernelbot_eval"
},
"measurement": {
"timer": "wall_clock",
"primaryStatistic": "mean"
},
"comparability": {
"notes": "Per-case wall-clock statistics as published in the KernelBot dataset. Comparable only within one leaderboard problem and GPU type; runner software versions ride each run's labels.",
"family": "gpumode_kernelbot"
}
},
"metadata": {
"name": "gpumode-kernelbot-eval",
"title": "GPU MODE KernelBot evaluation harness"
},
"apiVersion": "kernelindex.dev/v1alpha1"
},
"environment": {
"kind": "ExecutionEnvironment",
"spec": {
"hardware": {
"vendor": "amd",
"product": "AMD Instinct MI300X",
"architecture": "gfx942"
},
"software": {}
},
"metadata": {
"name": "gpumode-kernelbot-amd-instinct-mi300x",
"title": "KernelBot runner · AMD Instinct MI300X"
},
"apiVersion": "kernelindex.dev/v1alpha1"
}
}Cite this record (permalink, digest, access date)
Report an issue with this run
Published 2026-08-15 · GPU MODE KernelBot · June 9 Researcher Reciprocity License v1.0All results for AMD FP8 blockwise GEMM →JSON